NVIDIA
NVIDIA
Triton Inference Server
Container
NVIDIA
NVIDIA
Triton Inference Server

Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

LayerLabelCreated
sha256:36df1ef459d96ebea8b591d2c7b26618c84b60a648a416d2fcaef39c189b8f9aRUN
TRITON_VERSION=2.61.0 TRITON_CONTAINER_VERSION=25.09 pip3 install -r python/openai/requirements.txt
10/03/2025 5:31 PM UTC
sha256:c5c7e6cead9fa5d969ada667528fda885aafb8a7cae7fd74577bb4206ce3cc64RUN
TRITON_VERSION=2.61.0 TRITON_CONTAINER_VERSION=25.09 find /opt/tritonserver/python -maxdepth 1 -type f -name "tritonserver-*.whl" | xargs -I {} pip install --upgrade {}[all] &&
  find /opt/tritonserver/python -maxdepth 1 -type f -name "tritonfrontend-*.whl" | xargs -I {} pip install --upgrade {}[all]
10/03/2025 5:30 PM UTC
sha256:623803345b0c0deba639068c131b59b1096fc6788011173c66e3c8dc7880660fCOPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
10/03/2025 5:30 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt/tritonserver
10/03/2025 5:30 PM UTC
sha256:bc68afd5f8266f67915ded4ac539b6c4a88d45665f6f518c3b4c6aeee95580d3COPY
--chown=1000:1000 build/install tritonserver
10/03/2025 5:30 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt
10/03/2025 5:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.ref=e083729f123ef30ce5afc235aec51c3bcacb5c1a
10/03/2025 5:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.id=216994193
10/03/2025 5:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_BUILD_ID=216994193
10/03/2025 5:30 PM UTC
sha256:7c391456c0ce0e0a5124c88f2e87ebe846d7b7dda8b81eb0145fb74c70c80e54COPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
10/03/2025 5:30 PM UTC
...